The purpose of this little code is to automate the following two processes:
- to transcribe a PDF article in Hebrew into a TXT file using Tesseract.
- PDF are converted into PNGs in a temporary folder
- Each images are then converted into strings by Tesseract
- translate the TXT file into French using Google Translate.
Currently, the translation is not very good (and not as good as you'd expect from Google Translate online). It is a really work in progress code.